Dr. David Fajgenbaum

DFMO for Bachman-Bopp gets a score and DFMO for breast cancer gets a score.

And that's probably a low score because it's probably not going to work in breast cancer, but you get a score for every match.

And then you look at the things at the very top.

So you rank order the less and you say, what are the point nine nines, which basically the algorithm is saying this is like there's there's some heat here, right?

Like there's some there's probably something here

Maybe it's this drug, and DFMO Bachman-Bup's an example where like there's too much of this thing and this drug inhibits that thing.

And so it's like the match is being made even at that simple of a level.

Like in my case, there was too much of mTOR, that signaling pathway, and serolimus inhibits mTOR.

And so it's like it's looking for the—and most of the time it's not that simple, but—

It's looking for matches like that, and it's going to give a high score if there's something clear like that.

And then the other thing is we also generate a separate score.

We call it our unmet medical needs score, which is basically how bad is the disease.

So we score also the higher the score, the worse the disease, lower score, less bad the disease, because we want to be going after good matches for really bad diseases.

As you said before, we're a 50-member team with limited resources.

When you can go after any drug and any disease, there's a lot of opportunities.

But if we're going to spend our time on Earth going after the really bad diseases with the really good matches, and so we use both scores to get us started.

So do you actually sift through each drug?

It's not each disease.

It's each drug.

And it's actually not even each drug or each disease.